从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
编程
Luxury Resale Research
试用Compare luxury resale listings and sales
它能做什么
Research public, read-only marketplace data for luxury fashion, handbags, watches, sneakers, and streetwear. Use this skill when the user needs current asks, sold comparables where the source exposes them, listing-level condition, or seller/dealer context across luxury resale sources. It complement…
技能文档
Luxury resale research
Research public, read-only marketplace data for luxury fashion, handbags,
watches, sneakers, and streetwear. Use this skill when the user needs current
asks, sold comparables where the source exposes them, listing-level condition,
or seller/dealer context across luxury resale sources. It complements the broad
resale-secondhand-research skill; use this one when specialist luxury sources
or a disciplined evidence comparison matters.
Do not place orders, make offers, authenticate an item, estimate an appraisal, claim a purchase total, or imply that a platform's condition label proves authenticity. Do not infer fees, duties, shipping, or currency conversion when the selected public response does not state them.
Evidence workflow
- Define the comparability key first: brand, model/reference or style ID, material/color, size, condition, and region/currency where present. Search active and sold datasets separately; an asking price is not sale evidence.
- Discover opaque filters before searching. Use each platform's directory, categories, conditions, brands, models, or facets endpoint rather than guessing ids, slugs, or values.
- Pull a compact active set, then fetch detail only for credible matches. Keep source URL/path and the retrieval time for every record. Follow only the source's cursor/page limit; narrow the query instead of deep paging.
- Report separate fields for: active asks; sold evidence (sale price
and sale date only where the endpoint supplies both); condition and
authentication signals (source-stated, never independently verified);
fees/shipping/duties (stated amount or
not provided); currency; and source timestamp (listing/sale date if supplied, plus retrieval time). Do not pool currencies or condition grades without labeling the normalization assumption. - State evidence gaps plainly. Current inventory, recommendation rails, seller reputation, and marketplace-wide counts are useful context, not a transaction record or authenticity determination.
Source map
Use the exact routes and parameter names below. All are GET public-data
reads. Braces identify a path parameter; all others are query parameters.
Core luxury sources
- The RealReal: discovery:
therealreal_autocomplete(/therealreal/autocomplete,term),therealreal_categories,therealreal_conditions,therealreal_collections, andtherealreal_designers(category). Search:therealreal_search(/therealreal/search, requiredquery; optionalcategory_id,designer_id,condition_id,price_from,price_to,on_sale,available,after). Browse:therealreal_category(path,on_sale,available,after),therealreal_designer(slug,on_sale,available,after), andtherealreal_collection(slug,after). Detail:therealreal_listing(url) andtherealreal_similar(product_id). Reusenext_afterexactly as returned. - Fashionphile: discovery/catalog:
fashionphile_collectionsandfashionphile_products(page,limit; default 50, maximum 250), plusfashionphile_sitemapsandfashionphile_sitemap_urls(type,limit). Search:fashionphile_search(/fashionphile/search;q,condition,availability,vendor,sort,page,limit; default 20, maximum 50). Useavailability=soldspecifically for its sold archive;availableis the default andallis also accepted. Details:fashionphile_product(handle) andfashionphile_product_recommendations(handle,intent,limit; default 10, maximum 20;intentisrelatedorcomplementary). Collection and static-page reads usefashionphile_collection_products(handle,page,limit),fashionphile_pages(page,limit), andfashionphile_page(handle); suggestions usefashionphile_search_suggest(q,types,limit; maximum 20). - Rebag: use the same public storefront pattern with only Rebag routes:
rebag_search(/rebag/search;q,sort,page,limit),rebag_product(handle),rebag_product_recommendations(handle,intent,limit),rebag_productsandrebag_collections(page,limit; default 50, maximum 250),rebag_collection_products(handle,page,limit),rebag_search_suggest(q,types,limit; maximum 20),rebag_sitemaps,rebag_sitemap_urls(type,limit),rebag_pages(page,limit),rebag_page(handle), andrebag_store. - Vestiaire Collective: discovery:
vestiaire_brands,vestiaire_categories, andvestiaire_conditions. Search:vestiaire_search(/vestiaire/search;q,brand_id,category_id,condition_id,sort,page,per_page).per_pageis at most 60 andpage * per_pagemust not exceed 1000; use the returned directory IDs. Detail/context:vestiaire_product(path),vestiaire_search_sellers(q),vestiaire_seller(id), andvestiaire_suggest(q). - Grailed: discover filters with
grailed_categoriesand designers withgrailed_designers(q,page,limit); curated browse isgrailed_collectionsthengrailed_collection(id). Usegrailed_searchfor active asks andgrailed_sold_listingsfor sold evidence. Both acceptq,designer,department,category,size,color,condition,min_price,max_price,sort,page, andlimit; price filters mean final sold price on the sold route. Detail/context:grailed_listing(id),grailed_similar_listings(id,limit),grailed_seller(username,page,limit),grailed_seller_reviews(username,page), andgrailed_suggest(q). - Chrono24: discover
chrono24_brands, thenchrono24_models(brand), andchrono24_facets(group) before advanced filters. Search withchrono24_search(/chrono24/search; at leastqueryorbrand; optionalmodel,sort,page,page_size,condition,used_or_new,case_material,dial_color,bracelet_material,movement_type,gender,watch_type,stock_info). The UI page sizes are 30, 60, or 120. Usechrono24_listing(path) for the reference number, specifications, price/currency, condition, seller type, and location; dealer context ischrono24_dealer(slug) andchrono24_dealer_reviews(slug,page,page_size1–50,min_stars0–5,sort). Suggestions:chrono24_autocomplete(query).
Adjacent resale benchmarks
Use these only when they improve the requested comparison; do not substitute a streetwear marketplace for a luxury-listing comparable without saying so.
- Depop:
depop_search(queryplusbrand_ids,category,subcategory,condition,colours,sizes,gender,is_kids,on_sale,price_min,price_max,sort,after); discover withdepop_brands,depop_categories,depop_sizes, anddepop_search_facets(query). Detail/shop:/depop/item/{slug},/depop/item/{slug}/similar(after,limit, up to 150),depop_search_sellers(query), and/depop/shop/{username}with the compatible filters. Suggestions:depop_suggest(query). - Poshmark: use
poshmark_brandsandposhmark_categoriesfor discovery; active browse/search isposhmark_search(query,department,max_id),/poshmark/brand/{name}(max_id), or/poshmark/category/{path}(max_id). Details are/poshmark/listing/{id}; seller context is/poshmark/closet/{username}(max_id). Reusenext_max_idexactly. - GOAT and StockX: use product detail for market context, not a confirmed
sale comp unless the response explicitly provides a last-sale field.
goat_searchsupportsquery, facets,page, andlimit; discover withgoat_search_facets,goat_countries, andgoat_curated; detail is/goat/product/{slug}(country_code).stockx_searchsupportscategory,query, facet filters,page, andlimit; discoverstockx_categoriesandstockx_brands; detail is/stockx/product/{slug}.stockx_releases(from,page,limit) is a release calendar, not resale history.
Reporting shape
For a comparison, return a compact table or JSON list with one row per source
listing and include source, listing_url_or_path, status (active,
sold, or market_context), price, currency, condition_text,
authentication_signal, seller_or_dealer_signal, sale_date,
fees_shipping_duties, source_timestamp, and retrieved_at. Leave an
unsupported field null or label it not provided; never fill it with an
estimate. Keep active asks and sold evidence in separate summaries before any
user-requested comparison.
相关技能
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
编写、调试与调优 Playwright 测试,涵盖定位器策略、追踪诊断与 CI 友好的超时配置。
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
crawlora-org 的更多技能
浏览全部技能Researches Yahoo's editorial content network — Autos, Entertainment, Health, Life, News, Shopping, Sports, and Tech — via the Crawlora API, returning clean JSON. Each vertical shares a home/category story-stream plus full-article-content pattern; Yahoo Sports adds deeper sports-data endpoints (scoreboards, standings, team/player/roster, golf, MMA, motorsports, tennis, Olympics). Use when the user wants a Yahoo section's story feed, a Yahoo article's full content, Yahoo News comments, Yahoo Shopping deals/lists, or Yahoo Sports scores/standings/schedules. Yahoo Finance and Yahoo Search are covered by their own separate skills, not this one.
Fetches any company's job openings straight from its Applicant Tracking System (ATS) via the Crawlora API — Greenhouse, Lever, Workday, Ashby, SmartRecruiters, Workable, Personio, Recruitee, iCIMS, Oracle Recruiting, Rippling, Pinpoint, Eightfold, Gem, UKG, and Teamtailor — returning clean JSON. Use when the user wants every open role from a specific company's ATS-hosted career page, a single job posting's full detail, or a hiring-velocity snapshot for a company, given its ATS platform and company/board slug.
Researches products, prices, sellers, and reviews across major online marketplaces and big-box/specialty retailers (Amazon, eBay, Shopify stores, Shop.app, Target, Costco, Walmart, Nike, Zara, Adidas, Best Buy, Home Depot, Sephora, SHEIN, IKEA, Chewy, and more) using the Crawlora API, returning clean JSON. Use when the user asks to find a product, compare prices or sellers, track listings, or pull marketplace/retailer reviews — instead of scraping store pages.
Researches hotels, flights, attractions, short-term rentals, and live events via the Crawlora API — Booking.com, Expedia, Agoda, TripAdvisor, Trip.com, Airbnb, and Ticketmaster — returning clean JSON. Use when the user wants to search or compare hotel/stay prices and reviews, look up flight options, find attractions/things-to-do or concerts/events, or research an Airbnb host or listing.
Researches Zara's catalog — category taxonomy, category listings, product detail, keyword search, search suggestions, and nearby physical stores — using the Crawlora API, returning clean JSON. Use when the user asks to find a product on Zara, browse a Zara category, search Zara's catalog by keyword, pull a Zara product's colors/sizes/images, or find a nearby Zara store — instead of scraping zara.com.
Researches global news and US television coverage via the Crawlora API — GDELT web-news search/context/timeline/sentiment, plus GDELT Television 2.0 AI's index of US TV transcripts, captions, on-screen text, and visual labels — returning clean JSON. Use when the user wants coverage-volume or sentiment trends over time, cross-outlet news search, sentence-level co-occurrence search, or what US TV news said/showed about a topic — OSINT, media-monitoring, and political/social-science research.